AI models
Meditron-70B
Parameters
70B
Published
Nov 27, 2023
Meditron-70B is an AI model developed by Ecole Polytechnique Federale de Lausanne (EPFL) (Switzerland), first published in November 2023. It works in the language and medicine domain, on tasks such as language modeling/generation, question answering and medical diagnosis.
Epoch AI has no training-compute estimate for this model. The model has 70,000,000,000 parameters. It was trained on roughly 48.1B datapoints. Training ran on 128 NVIDIA A100 SXM4 80 GB for about 332 hours.
Access: Open weights (restricted use). Its weights are openly available. It is built on top of Llama 2-70B. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Ecole Polytechnique Federale de Lausanne (EPFL)
- Country of organization
- Switzerland
- Domain
- Language, Medicine
- Task
- Language modeling/generation, Question answering, Medical diagnosis
- Compute estimation method
- Hardware, Operation counting
- Parameters
- 70,000,000,000
- Dataset size
- 48.1B
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 128
- Training time
- 332 h
- Training power draw
- 101.5 kW
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Base model
- Llama 2-70B
- Epoch confidence
- Confident
More from Ecole Polytechnique Federale de Lausanne (EPFL)
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models